Biomedical Signal Processing and Control 41 (2018) 129–139 Contents lists available at ScienceDirect Biomedical Signal Processing and Control jo ur nal homepage: www.elsevier.com/locate/bspc A novel data acquisition and analyzing approach to spermiogram tests Hamza Osman Ilhan ∗ , Nizamettin Aydin Yildiz Technical University, Department of Computer Engineering, 34220 Istanbul, Turkey a r t i c l e i n f o Article history: Received 16 May 2017 Received in revised form 17 October 2017 Accepted 19 November 2017 Keywords: Video stabilization Descriptor Spermiogram Sperm counting Speed up robust features Binary robust invariant scalable keypoints Features from accelerated segment test a b s t r a c t Spermiogram tests are currently performed in two ways; computer assisted and visual assessment. Computerized techniques are costly and parameter dependent. Therefore, it is not preferred in many laboratories. Analysis based on visual assessment technique is subjective. In this study, we proposed a new computerized approach in which data acquisition is performed as in visual assessment, but anal- ysis is done by computer. This approach provides more generalized results, requires less parameters due to the usage of standard counting chambers as in visual assessment technique, and cheaper than the other computerized techniques. Proposed approach includes two modules; video stabilization and motile sperm detection module. Stabilization is a requirement because it is impossible to fix proposed approach in ocular part completely. Otherwise, vibration affects the detection process of motile sperms. In this respect, feature-matching video stabilization idea is firstly utilized within the video-microscopy concept. Several feature extraction techniques were tested to sustain more stable videos in stabilization module. Motile sperm detection algorithm is then adapted to evaluate the efficiency of video stabilization and analyzing part. In case of vibrated frame sequence, the detection of total motile sperms concludes immediate peak values while it is around average values in stable frames. Samples were also evaluated by an expert with the visual assessment technique. Comparative tables and figures emphasize that the pro- posed approach can be employed in laboratories due to the high correlation with the visual assessment results. © 2017 Elsevier Ltd. All rights reserved. 1. Introduction Infertility is a quite common health problem affecting people mentally and physically. According to World Health Organization (WHO), infertility rate is increased 50% in last 50 years [1]. Normal sperm number was reported as 120 billion/ml in 1938 [2]. How- ever, in 1990, it decreased to 58 billion [3]. Infertility is caused by many reasons such as unhealthy diet, adverse living conditions and radiation effect. Understanding the reason behind the problem is still a challenge. In this respect, medical doctors recommend the semen analysis tests called spermiogram as a first assessment. Spermiogram is a technique involving sperm counting and morphology analyses. Infertility is highly related with the sperm numbers, hence, counting process is crucial. Detection of motile sperm cell rate over given sample is the main criteria in counting analyses. Infertility zone is described in the manual published by WHO as the presence of the immotile detected sperm number as more than 70% of all sperms [1]. In this sense, correctly identified of motile sperm number mostly reveals the possible infertility prob- ∗ Corresponding author. E-mail address: hoilhan@yildiz.edu.tr (H.O. Ilhan). lem. Morphology test is also important process in selecting good quality sperm in vitro fertilization for the evaluation of fertility efficiencies. Tests are carried out using two evaluation techniques based on computerized or visual assessment [4]. Some laboratories utilize an automated analysis system named as Computer Aided Sperm Analysis (CASA) in computerized techniques. It is costly due to being an integrated system including embedded camera, micro- scope and computer. Additionally, system is a black box system. The parameters and results can not be reconfigured and verified by experts/doctors [5]. In visual assessment technique, different standardization equipments can be employed such as Makler [6], Hemocytometer [7], Neubauer [8] to generalize the cell numbers in per ml. According to [9], Makler is one of the promising materials and the most employed chamber in laboratories. There are several CASA systems in medical market. However, laboratories mostly prefer visual assessment technique due to their cost. Even if they utilize the CASA system, they also verify the results using visual assessment. However, it is impossible to observe all sperm cells over microscopy by manually. The error rate might depend on the expertness and the experiences of laboratory assis- tant [10]. In this sense, improving a computer based sperm counting system is a necessity to obtain more consistent and trustful evalu- ation process. https://doi.org/10.1016/j.bspc.2017.11.009 1746-8094/© 2017 Elsevier Ltd. All rights reserved.